Neural network classifiers for automated video surveillance
- Publication Type:
- Conference Proceeding
- Citation:
- Neural Networks for Signal Processing - Proceedings of the IEEE Workshop, 2003, 2003-January pp. 729 - 738
- Issue Date:
- 2003-01-01
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
2003002140.pdf | 474.22 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
© 2003 IEEE. In automated visual surveillance applications, detection of suspicious human behaviors is of great practical importance. However due to random nature of human movements, reliable classification of suspicious human movements can be very difficult. Artificial Neural Network (ANN) classifiers can perform well however their computational requirements can be very large for real time implementation. In this paper, a data-based modeling neural network such as Modified Probabilistic Neural Network (MPNN) is introduced which partitions the decision space nonlinearly in order to achieve reliable classification, however still with acceptable computations. The experiment shows that the compact MPNN attains good classification performance compared to t h a t of other larger conventional neural network based classifiers such as Multilayer Perceptron (MLP) and Self Organising Map (SOM).
Please use this identifier to cite or link to this item: